zelenioncode
/
dreambooth_sdxl
- Public
- 151 runs
Run zelenioncode/dreambooth_sdxl with an API
Use one of our client libraries to get started quickly. Clicking on a library will take you to the Playground tab where you can tweak different inputs, see the results, and copy the corresponding code to use in your own project.
Input schema
The fields you can use to run this model with an API. If you don't give a value for a field its default value will be used.
| Field | Type | Default value | Description |
|---|---|---|---|
| gender |
string
(enum)
|
woman
Options: woman, man |
Gender of person in training photo ( woman or man )
|
| name_model |
string
|
Dreambooth_sdxl
|
Give name for your .safetensors model
|
| send_to_huggingface |
boolean
|
False
|
Send folder have .safetensors model direct to your huggingface account
|
| token_huggingface |
string
|
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
|
If you use huggingface, enter your API TOKEN
|
| repo_id_huggingface |
string
|
WGlint/SafetensorsFromReplicate
|
If you use huggingface, enter repo_id to one of your project
|
| folder_huggingface |
string
|
|
Enter a path to download your .safetensors model. Default = ./
|
| input |
string
|
https://huggingface.co/WGlint/SafetensorsFromReplicate/resolve/main/input.zip
|
Direct link download with training picture (Only .zip file and picture in 1024px/1024px !)
|
| repeat_input |
integer
|
100
Min: 1 Max: 1000 |
Repeat of time GPU look training data ( e.g. 15 pictures * 100 repeat = 1500 steps )
|
| use_class_reg |
boolean
|
False
|
Use regulat classification picture
|
| repeat_class_reg |
integer
|
1
Min: 1 Max: 1000 |
Repeat of time GPU look class reg picture ( e.g. 5000 pictures * 2 repeat = 10000 steps cache latents )
|
| class_reg |
string
|
|
Direct link download for regular classification picture ( Default = class image of gender you use )
|
| model_sdxl |
string
(enum)
|
Stable Diffusion XL
Options: Stable Diffusion XL, RealVisXL_2, RealVisXL_3 |
Choice a model pretrained can run for SDXL training with dreambooth
|
| num_cpu_threads_per_process |
integer
|
4
Min: 1 Max: 10 |
Number CPU thread use with accelerate module
|
| resolution |
string
|
1024,1024
|
Resolution of your training picture data. WARNING ! Write in this formet : width,height ( e.g. 1024,1024 )
|
| vae |
string
|
stabilityai/sdxl-vae
|
VAE use for create model training
|
| lr_scheduler_num_cycles |
integer
|
1
Min: 1 Max: 1000 |
Num learning rate cycles for your training
|
| max_data_loader_n_workers |
integer
|
0
Max: 100 |
Maximun data loader for n workers you set
|
| learning_rate_te1 |
number
|
0.00001
|
Value for learning_rate te1
|
| learning_rate_te2 |
number
|
0.00001
|
Value for learning_rate te2
|
| learning_rate |
number
|
0.00001
|
Value for learning_rate
|
| lr_scheduler |
string
(enum)
|
constant
Options: constant, linear, cosine, cosine_with_restarts, polynomial, constant_with_warmup, adafactor |
Method use for learning rate scheduler
|
| train_batch_size |
integer
|
1
Min: 1 Max: 64 |
Select value for device max train step and speed the generation, WARINING ! High value = High value to have CUDA Memory
|
| max_train_steps |
integer
|
3000
Max: 25000 |
Number of step you want for your training, and in average 1000 steps = 10 minutes
|
| save_every_n_epochs |
integer
|
1
Min: 1 Max: 64 |
Number of epochs model you want
|
| mixed_precision |
string
(enum)
|
fp16
Options: no, fp16, bf16 |
Select if you want to use miwed precision
|
| save_precision |
string
(enum)
|
fp16
Options: no, fp16, bf16 |
Select if you want to use save precision
|
| optimizer_type |
string
(enum)
|
AdaFactor
Options: AdamW, AdamW8bit, PagedAdamW, PagedAdamW8bit, PagedAdamW32bit, Lion8bit, PagedLion8bit, Lion, SGDNesterov, SGDNesterov8bit, DAdaptation, DAdaptAdaGrad, DAdaptAdam, DAdaptAdan, DAdaptAdanIP, DAdaptLion, DAdaptSGD, AdaFactor |
Select a optimiser type
|
| scale_parameter |
boolean
|
False
|
Use scale parameter
|
| relative_step |
boolean
|
False
|
Use relative step
|
| warmup_init |
boolean
|
False
|
Use warmup init
|
| weight_decay |
number
|
0.01
|
Give a float value for weight decay
|
| bucket_reso_steps |
integer
|
64
Min: 1 Max: 1000 |
Give a int value for bucket reso steps
|
| save_every_n_steps |
integer
|
1
Min: 1 Max: 5 |
Number of .safetensors model you want, if you select 2 with 2000 max train steps, you well get 2 .safetensors. 1 with 1000 steps and 1 with 2000 steps
|
| noise_offset |
number
|
0
|
Give a float value for noise offset
|
| max_grad_norm |
number
|
0
|
Give a float value for max grad norm
|
| cache_latents_to_disk |
boolean
|
True
|
None
|
| cache_latents |
boolean
|
True
|
None
|
| mem_eff_attn |
boolean
|
True
|
None
|
| gradient_checkpointing |
boolean
|
True
|
None
|
| full_fp16 |
boolean
|
True
|
None
|
| xformers |
boolean
|
True
|
None
|
| bucket_no_upscale |
boolean
|
True
|
None
|
| no_half_vae |
boolean
|
True
|
None
|
| train_text_encoder |
boolean
|
True
|
None
|
| learning_rate_te1_bool |
number
|
0.000003
|
value for learning rate te1 bool
|
| learning_rate_te2_bool |
number
|
0
|
value for learning rate te2 bool
|
{
"type": "object",
"title": "Input",
"properties": {
"vae": {
"type": "string",
"title": "Vae",
"default": "stabilityai/sdxl-vae",
"x-order": 14,
"description": "VAE use for create model training"
},
"input": {
"type": "string",
"title": "Input",
"default": "https://huggingface.co/WGlint/SafetensorsFromReplicate/resolve/main/input.zip",
"x-order": 6,
"description": "Direct link download with training picture (Only .zip file and picture in 1024px/1024px !)"
},
"gender": {
"enum": [
"woman",
"man"
],
"type": "string",
"title": "gender",
"description": "Gender of person in training photo ( woman or man )",
"default": "woman",
"x-order": 0
},
"xformers": {
"type": "boolean",
"title": "Xformers",
"default": true,
"x-order": 40
},
"class_reg": {
"type": "string",
"title": "Class Reg",
"default": "",
"x-order": 10,
"description": "Direct link download for regular classification picture ( Default = class image of gender you use )"
},
"full_fp16": {
"type": "boolean",
"title": "Full Fp16",
"default": true,
"x-order": 39
},
"model_sdxl": {
"enum": [
"Stable Diffusion XL",
"RealVisXL_2",
"RealVisXL_3"
],
"type": "string",
"title": "model_sdxl",
"description": "Choice a model pretrained can run for SDXL training with dreambooth",
"default": "Stable Diffusion XL",
"x-order": 11
},
"name_model": {
"type": "string",
"title": "Name Model",
"default": "Dreambooth_sdxl",
"x-order": 1,
"description": "Give name for your .safetensors model"
},
"resolution": {
"type": "string",
"title": "Resolution",
"default": "1024,1024",
"x-order": 13,
"description": "Resolution of your training picture data. WARNING ! Write in this formet : width,height ( e.g. 1024,1024 )"
},
"no_half_vae": {
"type": "boolean",
"title": "No Half Vae",
"default": true,
"x-order": 42
},
"warmup_init": {
"type": "boolean",
"title": "Warmup Init",
"default": false,
"x-order": 29,
"description": "Use warmup init"
},
"lr_scheduler": {
"enum": [
"constant",
"linear",
"cosine",
"cosine_with_restarts",
"polynomial",
"constant_with_warmup",
"adafactor"
],
"type": "string",
"title": "lr_scheduler",
"description": "Method use for learning rate scheduler",
"default": "constant",
"x-order": 20
},
"mem_eff_attn": {
"type": "boolean",
"title": "Mem Eff Attn",
"default": true,
"x-order": 37
},
"noise_offset": {
"type": "number",
"title": "Noise Offset",
"default": 0,
"x-order": 33,
"description": "Give a float value for noise offset"
},
"repeat_input": {
"type": "integer",
"title": "Repeat Input",
"default": 100,
"maximum": 1000,
"minimum": 1,
"x-order": 7,
"description": "Repeat of time GPU look training data ( e.g. 15 pictures * 100 repeat = 1500 steps )"
},
"weight_decay": {
"type": "number",
"title": "Weight Decay",
"default": 0.01,
"x-order": 30,
"description": "Give a float value for weight decay"
},
"cache_latents": {
"type": "boolean",
"title": "Cache Latents",
"default": true,
"x-order": 36
},
"learning_rate": {
"type": "number",
"title": "Learning Rate",
"default": 1e-05,
"x-order": 19,
"description": "Value for learning_rate"
},
"max_grad_norm": {
"type": "number",
"title": "Max Grad Norm",
"default": 0,
"x-order": 34,
"description": "Give a float value for max grad norm"
},
"relative_step": {
"type": "boolean",
"title": "Relative Step",
"default": false,
"x-order": 28,
"description": "Use relative step"
},
"use_class_reg": {
"type": "boolean",
"title": "Use Class Reg",
"default": false,
"x-order": 8,
"description": "Use regulat classification picture"
},
"optimizer_type": {
"enum": [
"AdamW",
"AdamW8bit",
"PagedAdamW",
"PagedAdamW8bit",
"PagedAdamW32bit",
"Lion8bit",
"PagedLion8bit",
"Lion",
"SGDNesterov",
"SGDNesterov8bit",
"DAdaptation",
"DAdaptAdaGrad",
"DAdaptAdam",
"DAdaptAdan",
"DAdaptAdanIP",
"DAdaptLion",
"DAdaptSGD",
"AdaFactor"
],
"type": "string",
"title": "optimizer_type",
"description": "Select a optimiser type",
"default": "AdaFactor",
"x-order": 26
},
"save_precision": {
"enum": [
"no",
"fp16",
"bf16"
],
"type": "string",
"title": "save_precision",
"description": "Select if you want to use save precision",
"default": "fp16",
"x-order": 25
},
"max_train_steps": {
"type": "integer",
"title": "Max Train Steps",
"default": 3000,
"maximum": 25000,
"minimum": 0,
"x-order": 22,
"description": "Number of step you want for your training, and in average 1000 steps = 10 minutes"
},
"mixed_precision": {
"enum": [
"no",
"fp16",
"bf16"
],
"type": "string",
"title": "mixed_precision",
"description": "Select if you want to use miwed precision",
"default": "fp16",
"x-order": 24
},
"scale_parameter": {
"type": "boolean",
"title": "Scale Parameter",
"default": false,
"x-order": 27,
"description": "Use scale parameter"
},
"repeat_class_reg": {
"type": "integer",
"title": "Repeat Class Reg",
"default": 1,
"maximum": 1000,
"minimum": 1,
"x-order": 9,
"description": "Repeat of time GPU look class reg picture ( e.g. 5000 pictures * 2 repeat = 10000 steps cache latents )"
},
"train_batch_size": {
"type": "integer",
"title": "Train Batch Size",
"default": 1,
"maximum": 64,
"minimum": 1,
"x-order": 21,
"description": "Select value for device max train step and speed the generation, WARINING ! High value = High value to have CUDA Memory"
},
"bucket_no_upscale": {
"type": "boolean",
"title": "Bucket No Upscale",
"default": true,
"x-order": 41
},
"bucket_reso_steps": {
"type": "integer",
"title": "Bucket Reso Steps",
"default": 64,
"maximum": 1000,
"minimum": 1,
"x-order": 31,
"description": "Give a int value for bucket reso steps"
},
"learning_rate_te1": {
"type": "number",
"title": "Learning Rate Te1",
"default": 1e-05,
"x-order": 17,
"description": "Value for learning_rate te1"
},
"learning_rate_te2": {
"type": "number",
"title": "Learning Rate Te2",
"default": 1e-05,
"x-order": 18,
"description": "Value for learning_rate te2"
},
"token_huggingface": {
"type": "string",
"title": "Token Huggingface",
"default": "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",
"x-order": 3,
"description": "If you use huggingface, enter your API TOKEN"
},
"folder_huggingface": {
"type": "string",
"title": "Folder Huggingface",
"default": "",
"x-order": 5,
"description": "Enter a path to download your .safetensors model. Default = ./"
},
"save_every_n_steps": {
"type": "integer",
"title": "Save Every N Steps",
"default": 1,
"maximum": 5,
"minimum": 1,
"x-order": 32,
"description": "Number of .safetensors model you want, if you select 2 with 2000 max train steps, you well get 2 .safetensors. 1 with 1000 steps and 1 with 2000 steps"
},
"train_text_encoder": {
"type": "boolean",
"title": "Train Text Encoder",
"default": true,
"x-order": 43
},
"repo_id_huggingface": {
"type": "string",
"title": "Repo Id Huggingface",
"default": "WGlint/SafetensorsFromReplicate",
"x-order": 4,
"description": "If you use huggingface, enter repo_id to one of your project"
},
"save_every_n_epochs": {
"type": "integer",
"title": "Save Every N Epochs",
"default": 1,
"maximum": 64,
"minimum": 1,
"x-order": 23,
"description": "Number of epochs model you want"
},
"send_to_huggingface": {
"type": "boolean",
"title": "Send To Huggingface",
"default": false,
"x-order": 2,
"description": "Send folder have .safetensors model direct to your huggingface account"
},
"cache_latents_to_disk": {
"type": "boolean",
"title": "Cache Latents To Disk",
"default": true,
"x-order": 35
},
"gradient_checkpointing": {
"type": "boolean",
"title": "Gradient Checkpointing",
"default": true,
"x-order": 38
},
"learning_rate_te1_bool": {
"type": "number",
"title": "Learning Rate Te1 Bool",
"default": 3e-06,
"x-order": 44,
"description": "value for learning rate te1 bool"
},
"learning_rate_te2_bool": {
"type": "number",
"title": "Learning Rate Te2 Bool",
"default": 0,
"x-order": 45,
"description": "value for learning rate te2 bool"
},
"lr_scheduler_num_cycles": {
"type": "integer",
"title": "Lr Scheduler Num Cycles",
"default": 1,
"maximum": 1000,
"minimum": 1,
"x-order": 15,
"description": "Num learning rate cycles for your training"
},
"max_data_loader_n_workers": {
"type": "integer",
"title": "Max Data Loader N Workers",
"default": 0,
"maximum": 100,
"minimum": 0,
"x-order": 16,
"description": "Maximun data loader for n workers you set"
},
"num_cpu_threads_per_process": {
"type": "integer",
"title": "Num Cpu Threads Per Process",
"default": 4,
"maximum": 10,
"minimum": 1,
"x-order": 12,
"description": "Number CPU thread use with accelerate module"
}
}
}
Output schema
The shape of the response you’ll get when you run this model with an API.
Schema
{
"type": "string",
"title": "Output",
"format": "uri"
}